Deep learning–based estimation of sagittal spinal alignment from coronal radiographs
Frontiers in Bioengineering and Biotechnology · 20.07.2026 · 14
DOI: 10.3389/fbioe.2026.1843705 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 20.07.2026. Verfasst von Tito Bassani und 3 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Biological Structures Mechanics, IRCCS Istituto Ortopedico Galeazzi, Milan, Italy. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministero della Salute.
Abstract (Originalsprache)
Introduction
Patient-specific sagittal alignment parameters are essential for accurate biomechanical modeling of the spine. These parameters are typically derived from biplanar radiographs, which, despite low-dose advancements, still involve cumulative radiation exposure. Deep learning has shown promise in automating radiographic analysis; however, prior approaches for cross-plane prediction—such as generating sagittal images from coronal views using generative adversarial networks (GANs)—have not achieved clinically acceptable accuracy. This study investigates an alternative strategy based on multiple-output regression (MOR) to directly predict sagittal parameters from coronal radiographs and evaluates its performance against GAN-based approach.
Methods
A dataset of 449 adult subjects with EOS biplanar radiographs was used to train (313 subjects, 70% of dataset), validate and test (68 subjects, 15%, each) a MOR model based on convolutional neural networks. Six sagittal parameters (TK, LL, SS, PI, PT, SVA) were predicted from preprocessed coronal images. Model performance was assessed using absolute error metrics, regression analysis, Bland–Altman plots, and Lin’s concordance correlation coefficient (CCC). External inference was evaluated on an independent dataset of 69 adolescents with idiopathic scoliosis (AIS), enabling comparison between MOR predictions and parameters derived from GAN-generated sagittal images.
Results
In the adult test set, median absolute errors ranged from 4° to 8° for angular parameters and 1.6 cm for SVA, with maximum errors up to 40° and 8.8 cm. CCC values varied from 0.20 (PI) to 0.69 (PT), indicating moderate agreement for some parameters and weak agreement for others. Regression and Bland–Altman analyses revealed both proportional and fixed biases. In the AIS dataset, MOR and GAN-based approaches showed comparable performance (median errors ∼7°), although GAN performed better for SVA (1 cm vs. 2 cm; p-value <0.001). Both methods exhibited reduced accuracy and lower CCC values compared with the adult dataset.
Discussion
Direct prediction of sagittal alignment parameters from coronal radiographs using MOR yields limited accuracy and is affected by systematic biases. Comparable performance with GAN-based methods suggests that the primary limitation lies in the insufficient sagittal information contained in coronal projections. Current deep learning approaches are therefore inadequate to replace biplanar imaging for reliable sagittal assessment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratory of Biological Structures Mechanics, IRCCS Istituto Ortopedico Galeazzi, Milan, Italy.
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy.
- Department of Biomedical Sciences for Health, University of Milan, Milan, Italy.
- Unit of Diagnostic and Interventional Radiology, IRCCS Istituto Ortopedico Galeazzi, Milan, Italy.
Förderung
- Ministero della Salute
Zitieren
APA
Bassani, T., Cecchinato, R., Brayda-Bruno, M., & Sconfienza, L. M. (2026). Deep learning–based estimation of sagittal spinal alignment from coronal radiographs. Frontiers in Bioengineering and Biotechnology, 14. https://doi.org/10.3389/fbioe.2026.1843705
Vancouver
Bassani T, Cecchinato R, Brayda-Bruno M, Sconfienza LM. Deep learning–based estimation of sagittal spinal alignment from coronal radiographs. Frontiers in Bioengineering and Biotechnology. 2026;14. doi:10.3389/fbioe.2026.1843705
BibTeX
@article{Bassani2026,
author = {Bassani, Tito and Cecchinato, Riccardo and Brayda-Bruno, Marco and Sconfienza, Luca Maria},
title = {Deep learning–based estimation of sagittal spinal alignment from coronal radiographs},
journal = {Frontiers in Bioengineering and Biotechnology},
year = {2026},
volume = {14},
doi = {10.3389/fbioe.2026.1843705}
}
EUVIMED